Determining transactional networks using transactional data

Abstract

Various methods are provided for determining transactional networks using transactional data. One example method may comprise receiving a set of transactional data associated each of a plurality of customers, the set of the transactional data comprising a plurality of ordered lists of elements, each ordered list of elements defining a transaction of a plurality of transactions, the ordered list of elements comprising information identifying a particular customer from the plurality of customers, a merchant, and a timestamp, for each particular customer from the plurality of customers, generating a network, each generated network comprising one or more merchant nodes, a plurality of customer nodes, one or more merchant-customer edges between at least one of the one or more merchant nodes and at least one of the plurality of customer nodes, and one or more customer-customer edges between two or more customer nodes.

What is claimed: 
     
       1. A method comprising:
 receiving a set of transactional data associated with a plurality of merchants and a plurality of customers, the set of transactional data comprising a plurality of ordered lists of elements, each ordered list of elements defining a selected transaction of a plurality of transactions, the ordered list of elements comprising a customer, a merchant and a timestamp; 
 receiving social data associated with the plurality of customers via an application programming interface; 
 for each customer of the plurality of customers, generating, via a processor, one or more networks, 
 wherein generation of each network of the one or more networks is performed by: 
 (1) determining transaction data for a selected customer of the plurality of customers; 
 (2) determining one or more transaction merchants with whom the selected customer has transacted based on the transaction data; and 
 (3) computing a set of additional customers, each of which having subsequently transacted with the one or more transaction merchants with whom the selected customer transacted with, 
 wherein each network comprises one or more merchant nodes, a plurality of customer nodes, one or more merchant-customer edges between at least one of the one or more merchant nodes and at least one of the plurality of customer nodes, one or more customer-customer edges between two or more customer nodes of the plurality of customer nodes, and a plurality of weight values each associated with at least one of the merchant-customer edges or the one or more customer-customer edges, wherein the plurality of weight values are derived based at least in part on the social data; 
 generating, via the processor, a network ranking of a particular customer node of the plurality of customer nodes based at least in part on a centrality of the particular customer node within at least one of the one or more networks, and wherein the centrality is determined at least in part based on the plurality of weight values; and 
 utilizing the network ranking of the particular customer node to determine whether to transmit a promotion to the selected customer, 
 wherein utilization of the network ranking of the particular customer node to determine whether to transmit the promotion to the selected customer comprises: 
 determining if the network ranking of the particular customer node meets a predetermined threshold; and 
 in an instance in which the particular customer node satisfies the predetermined threshold, transmitting the promotion. 
 
     
     
       2. The method of  claim 1 , wherein the one or more merchant nodes identify each of the one or more transaction merchants with whom the selected customer has transacted. 
     
     
       3. The method of  claim 1 , wherein each of the plurality of customer nodes include a node identifying one or the set of additional customers. 
     
     
       4. The method of  claim 1 , wherein the one or more merchant-customer edges are defined based on a first transaction occurring between the merchant and the customer as indicated in the transactional data. 
     
     
       5. The method of  claim 1 , wherein the one or more customer-customer edges are defined based on each of the two or more customer nodes being associated with at least one transaction with a same particular merchant. 
     
     
       6. The method of  claim 1 , further comprising:
 computing centrality measures for one or more of the plurality of customer nodes from the transactional data; 
 classifying customers into different segments by applying data clustering strategies and pattern recognition algorithms on the transactional data; and 
 clustering the customers according to the transactional data. 
 
     
     
       7. The method of  claim 6 , wherein the pattern recognition algorithms include one or more of unsupervised learning, semi-supervised learning, supervised learning, reinforcement learning, association rules learning, Bayesian learning, and solving for probabilistic graphical models. 
     
     
       8. The method of  claim 1 , further comprising:
 distinguishing, using a general object ranking algorithm, between different objects within a given one of the one or more networks, wherein the different objects include nodes of the given network; 
 computing linking analysis measures for the customers and the merchants; 
 identifying a set of most influential customers among the plurality of customers; and 
 transmitting a promotion to the set of most influential customers. 
 
     
     
       9. A computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code instructions stored therein, the computer-executable program code instructions comprising program code instructions for:
 receiving a set of transactional data associated with a plurality of merchants and a plurality of customers, the set of transactional data comprising a plurality of ordered lists of elements, each ordered list of elements defining a selected transaction of a plurality of transactions, the ordered list of elements comprising a customer, a merchant and a timestamp; 
 receiving social data associated with the plurality of customers via an application programming interface; 
 for each customer of the plurality of customers, generating, via a processor, one or more networks, 
 wherein generation of each network of the one or more networks is performed by: 
 (1) determining transaction data for a selected customer of the plurality of customers; 
 (2) determining one or more transaction merchants with whom the selected customer has transacted based on the transaction data; and 
 (3) computing a set of additional customers, each of which having subsequently transacted with the one or more transaction merchants with whom the selected customer transacted with, 
 wherein each network comprises one or more merchant nodes, a plurality of customer nodes, one or more merchant-customer edges between at least one of the one or more merchant nodes and at least one of the plurality of customer nodes, one or more customer-customer edges between two or more customer nodes of the plurality of customer nodes, and a plurality of weight values each associated with at least one of the merchant-customer edges or the one or more customer-customer edges, wherein the plurality of weight values are derived based at least in part on the social data; 
 generating, via the processor, a network ranking of a particular customer node of the plurality of customer nodes based at least in part on a centrality of the particular customer node within at least one of the one or more networks, and wherein the centrality is determined at least in part based on the plurality of weight values; and 
 utilizing the network ranking of the particular customer node to determine whether to transmit a promotion to the selected customer, 
 wherein utilization of the network ranking of the particular customer node to determine whether to transmit the promotion to the selected customer comprises: 
 determining if the network ranking of the particular customer node meets a predetermined threshold; and 
 in an instance in which the particular customer node satisfies the predetermined threshold, transmitting the promotion. 
 
     
     
       10. The computer program product of  claim 9 , wherein the one or more merchant nodes identify each of the one or more transaction merchants with whom the selected customer has transacted. 
     
     
       11. The computer program product of  claim 9 , wherein each of the plurality of customer nodes include a node identifying one or the set of additional customers. 
     
     
       12. The computer program product of  claim 9 , wherein the one or more merchant-customer edges are defined based on a first transaction occurring between the merchant and the customer as indicated in the transactional data. 
     
     
       13. The computer program product of  claim 9 , wherein the one or more customer-customer edges are defined based on each of the two or more customer nodes being associated with at least one transaction with a same particular merchant. 
     
     
       14. The computer program product of  claim 9 , wherein the computer-executable program code instructions further comprise program code instructions for:
 computing centrality measures for one or more of the plurality of customer nodes from the transactional data; 
 classifying customers into different segments by applying data clustering strategies and pattern recognition algorithms on the transactional data; and 
 clustering the customers according to the transactional data. 
 
     
     
       15. The computer program product of  claim 9 , wherein the computer-executable program code instructions further comprise program code instructions for:
 distinguishing, using a general object ranking algorithm, between different objects within a given one of the one or more networks, wherein the different objects include nodes of the given network; 
 computing linking analysis measures for the customers and the merchants; 
 identifying a set of most influential customers among the plurality of customers; and 
 transmitting a promotion to the set of most influential customers. 
 
     
     
       16. An apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the processor, cause the apparatus to at least:
 receive a set of transactional data associated with a plurality of merchants and a plurality of customers, the set of transactional data comprising a plurality of ordered lists of elements, each ordered list of elements defining a selected transaction of a plurality of transactions, the ordered list of elements comprising a customer, a merchant and a timestamp; 
 receive social data associated with the plurality of customers via an application programming interface; 
 for each customer of the plurality of customers, generate, via a processor, one or more networks, 
 wherein generation of each network of the one or more networks is performed by: 
 (1) determining transaction data for a selected customer of the plurality of customers; 
 (2) determining one or more transaction merchants with whom the selected customer has transacted based on the transaction data; and 
 (3) computing a set of additional customers, each of which having subsequently transacted with the one or more transaction merchants with whom the selected customer transacted with, 
 wherein each network comprises one or more merchant nodes, a plurality of customer nodes, one or more merchant-customer edges between at least one of the one or more merchant nodes and at least one of the plurality of customer nodes, one or more customer-customer edges between two or more customer nodes of the plurality of customer nodes, and a plurality of weight values each associated with at least one of the merchant-customer edges or the one or more customer-customer edges, wherein the plurality of weight values are derived based at least in part on the social data; 
 generate, via the processor, a network ranking of a particular customer node of the plurality of customer nodes based at least in part on a centrality of the particular customer node within at least one of the one or more networks, and wherein the centrality is determined at least in part based on the plurality of weight values; and 
 utilize the network ranking of the particular customer node to determine whether to transmit a promotion to the selected customer, 
 wherein utilization of the network ranking of the particular customer node to determine whether to transmit the promotion to the selected customer comprises: 
 determine if the network ranking of the particular customer node meets a predetermined threshold; and 
 in an instance in which the particular customer node satisfies the predetermined threshold, transmit the promotion. 
 
     
     
       17. The apparatus of  claim 16 , wherein the one or more merchant nodes identify each of the one or more transaction merchants with whom the selected customer has transacted. 
     
     
       18. The apparatus of  claim 16 , wherein each of the plurality of customer nodes include a node identifying one or the set of additional customers. 
     
     
       19. The apparatus of  claim 16 , wherein the one or more merchant-customer edges are defined based on a first transaction occurring between the merchant and the customer as indicated in the transactional data. 
     
     
       20. The apparatus of  claim 16 , wherein the one or more customer-customer edges are defined based on each of the two or more customer nodes being associated with at least one transaction with a same particular merchant.